Triple
T11614501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Too Marvelous for Words |
E275469
|
entity |
| Predicate | introducedBy |
P513
|
FINISHED |
| Object | Dick Powell |
E166970
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Dick Powell | Statement: [Too Marvelous for Words, introducedBy, Dick Powell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dick Powell Context triple: [Too Marvelous for Words, introducedBy, Dick Powell]
-
A.
Dick Powell
chosen
Dick Powell was an American actor, singer, and later film director and producer, known for his transition from light musical roles to hard-boiled film noir leads in the 1930s and 1940s.
-
B.
Zachary Scott
Zachary Scott was an American actor best known for his suave yet often villainous roles in 1940s and 1950s Hollywood films.
-
C.
Robert Cummings
Robert Cummings was an American film and television actor best known for his roles in comedies and thrillers during Hollywood’s Golden Age.
-
D.
Victor Mature
Victor Mature was an American film actor known for his rugged leading-man roles in 1940s and 1950s Hollywood epics and adventure films.
-
E.
Glenn Ford
Glenn Ford was a Canadian-American film actor renowned for his versatile performances in classic Hollywood movies such as "Gilda," "The Big Heat," and "Blackboard Jungle."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a044a3088190b92f4674c2d0b443 |
completed | April 10, 2026, 7:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef1330cfc0819086a07139b6c82c10 |
completed | April 27, 2026, 7:41 a.m. |
Created at: April 8, 2026, 9:38 p.m.